Speaker verification is to judge the similarity of two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small intra-speaker distances and large inter-speaker distances.We propose a novel model named Voice Transformer(VOT) for speaker verification. The model consists of multiple parallel Transformers, and the outputs of these Transformers are adaptively combined. Deeply-Fused Semantic Memory Network(DFSMN)is integrated into the attention parts of these Transformers to capture long-distance information and enhance the local dependencies. Statistical pooling layers are incorporated to enhance overall performance without significantly increasing the number of parameters. We propose a new loss function called Additive Angular Margin Focal Loss(AAMF) to address the hard sample mining issue.We evaluate the proposed approach on the VoxCeleb1 and CN-Celeb2 datasets. The experimental results demonstrate that VOT achieves state-of-the-art results, outperforming nearly all existing models. The code is available on GitHub.

翻译：说话人验证旨在判断开放集中两段未知语音的相似性，理想的说话人嵌入应能将判别信息压缩为紧凑的语句级表征，使得类内距离小、类间距离大。我们提出了一种名为语音变换器（Voice Transformer, VOT）的新型模型用于说话人验证。该模型由多个并行Transformer构成，其输出通过自适应方式融合。深度融合语义记忆网络（Deeply-Fused Semantic Memory Network, DFSMN）被集成至这些Transformer的注意力部分，以捕获长距离信息并增强局部依赖性。统计池化层的加入在不过度增加参数量的前提下提升了整体性能。我们提出了一种名为加性角度间隔焦点损失（Additive Angular Margin Focal Loss, AAMF）的新损失函数，以解决难样本挖掘问题。在VoxCeleb1和CN-Celeb2数据集上的评估表明，VOT取得了最先进的结果，性能优于几乎所有现有模型。相关代码已开源在GitHub上。